Deep Learning for Multimedia Processing Applications

CHAPTER 9 Human Action Recognition Using ConvLSTM with Adversarial Noise and Compressive-Sensing-Based Dimensionality Reduction, Concise and Informative

Mohsin Raza Siyal¹, Mansoor Ebrahim¹, Syed Hasan Adil¹, Kamran Raza¹, and Nadeem Qazi²

¹Faculty of Engineering, Sciences and Technology, Iqra University, Karachi, Pakistan

²School of Architecture, Computing and Engineering, University of East London, London, UK

DOI: 10.1201/9781032646268-9

9.1 Introduction

In recent years, compressive sensing has intrigued many researchers from computer vision, digital signal, and information theory communities. The motive of interest is because of many applications, such as data compression, medical imaging, storage, digital image processing, transmission, ...